Issue with scaling with X3

[Ashu7397]

On trying to train the model for X3 scale, I am getting a runtime error:
Args: --chop --batch_size 4 --model CSNLN --patch_size 96 --save CSNLN_x2 --n_feats 128 --depth 12 --data_train DIV2K --save_models

src/model/attention.py:
yi = F.conv_transpose2d(yi, wi_center, stride=self.stride*self.scale, padding=self.scale)
RuntimeError: Given transposed=1, weight of size 121 128 9 9, expected input[1, 100, 32, 32] to have 121 channels, but got 100 channels instead

Other scales like X2 and X4 work well.

[SitthipongPed]

You need to change patch size for x3 as 144. Actually, the patch size should be 96, 144 ,192 for x2, x3, x4 respectively